{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:39:37Z","timestamp":1760132377135,"version":"3.37.3"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2015,12,19]],"date-time":"2015-12-19T00:00:00Z","timestamp":1450483200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100003451","name":"Euskal Herriko Unibertsitatea (ES)","doi-asserted-by":"publisher","award":["GIU13\/28"],"award-info":[{"award-number":["GIU13\/28"]}],"id":[{"id":"10.13039\/501100003451","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Lang Resources & Evaluation"],"published-print":{"date-parts":[[2016,6]]},"DOI":"10.1007\/s10579-015-9324-5","type":"journal-article","created":{"date-parts":[[2015,12,19]],"date-time":"2015-12-19T06:03:28Z","timestamp":1450505008000},"page":"221-243","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":10,"title":["KALAKA-3: a database for the assessment of spoken language recognition technology on YouTube audios"],"prefix":"10.1007","volume":"50","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9313-2667","authenticated-orcid":false,"given":"Luis Javier","family":"Rodr\u00edguez-Fuentes","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mikel","family":"Penagarikano","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Amparo","family":"Varona","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mireia","family":"Diez","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Germ\u00e1n","family":"Bordel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2015,12,19]]},"reference":[{"key":"9324_CR1","doi-asserted-by":"crossref","unstructured":"Bertoldi, N., & Federico, M. (2003). Cross-language spoken document retrieval on the TREC SDR collection. In Advances in Cross-Language Information Retrieval. Lecture Notes in Computer Science (Vol. 2785\/2003, pp. 476\u2013481). New York: Springer.","DOI":"10.1007\/978-3-540-45237-9_41"},{"key":"9324_CR2","unstructured":"Br\u00fcmmer, N (2008). FoCal: Toolkit for evaluation, fusion and calibration of statistical pattern recognizers. https:\/\/sites.google.com\/site\/nikobrummer\/focal ."},{"key":"9324_CR3","doi-asserted-by":"crossref","unstructured":"Br\u00fcmmer, N., & van Leeuwen, D. (2006). On calibration of language recognition scores. In Proceedings of Odyssey: The speaker and language recognition workshop, pp. 1\u20138.","DOI":"10.1109\/ODYSSEY.2006.248106"},{"issue":"4","key":"9324_CR4","doi-asserted-by":"crossref","first-page":"788","DOI":"10.1109\/TASL.2010.2064307","volume":"19","author":"N Dehak","year":"2011","unstructured":"Dehak, N., Kenny, P., Dehak, R., Dumouchel, P., & Outlet, P. (2011). Front-end factor analysis for speaker verification. IEEE Transactions on Audio, Speech, and Language Processing, 19(4), 788\u2013798.","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"9324_CR5","doi-asserted-by":"crossref","unstructured":"D\u2019Haro, L.F., Glembek, O., Plchot, O., Matejka, P., Soufifar, M., Cordoba, R., et al. (2012). Phonotactic language recognition using i-vectors and phoneme posteriorgram counts. In Interspeech 2012, Portland (OR), USA.","DOI":"10.21437\/Interspeech.2012-21"},{"key":"9324_CR6","doi-asserted-by":"crossref","unstructured":"D\u2019Haro, L. F., de C\u00f3rdoba, R., Caraballo, M. A., & Pardo, J. M. (2013). Low-resource language recognition using a fusion of phoneme posteriorgram counts, acoustic and glottal-based I-vectors. In Proceedings of ICASSP (pp. 6852\u20136856). Canada: Vancouver.","DOI":"10.1109\/ICASSP.2013.6638989"},{"key":"9324_CR7","doi-asserted-by":"crossref","unstructured":"D\u2019Haro, L. F., de C\u00f3rdoba, R., Palacios, C. S., & Echeverry, J. D. (2014a). Extended phone log-likelihood ratio features and acoustic-based i-vectors for language recognition. In Proceedings of ICASSP (pp. 5342\u20135346). Italy: Florence.","DOI":"10.1109\/ICASSP.2014.6854623"},{"key":"9324_CR8","doi-asserted-by":"crossref","unstructured":"D\u2019Haro, L.F., C\u00f3rdoba, R., Salamea, C., & Ferreiros, J. (2014b). Language recognition using phonotactic-based shifted delta coefficients and multiple phone recognizers. In Proceedings of interspeech, Singapore, pp. 3042\u20133046.","DOI":"10.21437\/Interspeech.2014-610"},{"key":"9324_CR9","doi-asserted-by":"crossref","unstructured":"Diez, M., Varona, A., Penagarikano, M., Rodriguez-Fuentes, L. J., & Bordel, G. (2012). On the use of log-likelihood ratios as features in spoken language recognition. In IEEE workshop on spoken language technology (SLT), Miami, Florida, USA.","DOI":"10.1109\/SLT.2012.6424235"},{"key":"9324_CR10","unstructured":"Fan, R. E., Chang, K. W., Hsieh, C. J., Wang, X. R., & Lin, C. J. (2008). LIBLINEAR: A library for large linear classification. Journal of Machine Learning Research, 9, 1871\u20131874. Software available at http:\/\/www.csie.ntu.edu.tw\/~cjlin\/liblinear ."},{"issue":"1","key":"9324_CR11","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1109\/TASL.2006.876860","volume":"15","author":"H Li","year":"2007","unstructured":"Li, H., Ma, B., & Lee, C. H. (2007). A vector space modeling approach to spoken language identification. IEEE Transactions on Audio, Speech and Language Processing, 15(1), 271\u2013284.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"issue":"5","key":"9324_CR12","doi-asserted-by":"crossref","first-page":"1136","DOI":"10.1109\/JPROC.2012.2237151","volume":"101","author":"H Li","year":"2013","unstructured":"Li, H., Ma, B., & Lee, K. A. (2013). Spoken language recognition: From fundamentals to practice. Proceedings of the IEEE, 101(5), 1136\u20131159.","journal-title":"Proceedings of the IEEE"},{"key":"9324_CR13","doi-asserted-by":"crossref","unstructured":"Ma, B., Guan, C., Li, H., & Lee, C. H. (2002). Multilingual speech recognition with language identification. In Proceedings of ICSLP (Interspeech), pp 505\u2013508.","DOI":"10.21437\/ICSLP.2002-178"},{"key":"9324_CR14","unstructured":"Martin, A. F., Greenberg, C. S., Howard, J. M., Doddington, G. R., & Godfrey, J. J. (2014). NIST language recognition evaluation past and future. In Proceedings of Odyssey: The speaker and language recognition workshop (pp. 145\u2013151). Finland: Joensuu."},{"key":"9324_CR15","doi-asserted-by":"crossref","unstructured":"Martinez, D., Plchot, O., Burget, L., Glembek O, & Matejka, P. (2011). Language recognition in iVectors space. In Proceedings of interspeech, pp 861\u2013864.","DOI":"10.21437\/Interspeech.2011-329"},{"key":"9324_CR16","doi-asserted-by":"crossref","unstructured":"Mart\u00ednez, D., Burget, L., Ferrer, L., & Scheffer, N. (2012). iVector-based Prosodic system for language identification. In Proceedings of ICASSP, Japan, pp 4861\u20134864.","DOI":"10.1109\/ICASSP.2012.6289008"},{"key":"9324_CR17","unstructured":"Matejka, P., Schwarz, P., Cernocky, J., & Chytil, P. (2005). Phonotactic language identification using high quality phoneme recognition. In Proceedings of interspeech (pp. 2237\u20132241). Portugal: Lisboa."},{"key":"9324_CR18","doi-asserted-by":"crossref","unstructured":"Penagarikano, M., Varona, A., Rodriguez-Fuentes, L. J., & Bordel, G. (2011a). Dimensionality reduction for using high-order n-grams in SVM-based phonotactic language recognition. In Proceedings of interspeech 2011 (pp. 853\u2013856). Italy: Florence.","DOI":"10.1109\/ICASSP.2011.5947332"},{"key":"9324_CR19","doi-asserted-by":"crossref","unstructured":"Penagarikano, M., Varona, A., Rodr\u00edguez-Fuentes, L. J., & Bordel, G. (2011b). A dynamic approach to the selection of high-order n-grams in phonotactic language recognition. In Proceedings of ICASSP (pp. 4412\u20134415). Prague: Czech Republic.","DOI":"10.1109\/ICASSP.2011.5947332"},{"issue":"8","key":"9324_CR20","doi-asserted-by":"crossref","first-page":"2348","DOI":"10.1109\/TASL.2011.2134088","volume":"19","author":"M Penagarikano","year":"2011","unstructured":"Penagarikano, M., Varona, A., Rodr\u00edguez-Fuentes, L. J., & Bordel, G. (2011c). Improved modeling of cross-decoder phone co-occurrences in SVM-based phonotactic language recognition. IEEE Transactions on Audio, Speech and Language Processing, 19(8), 2348\u20132363.","journal-title":"IEEE Transactions on Audio, Speech and Language Processing"},{"key":"9324_CR21","doi-asserted-by":"crossref","unstructured":"Richardson, F., & Campbell, W. (2008). Language recognition with discriminative keyword selection. In Proceedings of ICASSP, pp 4145\u20134148.","DOI":"10.1109\/ICASSP.2008.4518567"},{"key":"9324_CR22","unstructured":"Rodriguez-Fuentes, L.J., Penagarikano, M., Bordel, G., & Varona, A. (2010a). The Albayzin 2008 language recognition evaluation. In Proceedings of Odyssey: The speaker and language recognition workshop, pp 172\u2013179."},{"key":"9324_CR23","unstructured":"Rodriguez-Fuentes, L. J., Penagarikano, M., Bordel, G., Varona, A., & Diez, M. (2010b). KALAKA: A TV broadcast speech database for the evaluation of language recognition systems. In Proceedings of the 7th international conference on language resources and evaluation (LREC 2010) (pp. 1678\u20131685). Malta: Valleta."},{"key":"9324_CR24","doi-asserted-by":"crossref","unstructured":"Rodriguez-Fuentes, L. J., Penagarikano, M., Varona, A., Diez, M., & Bordel, G. (2011). The Albayzin 2010 language recognition evaluation. In Proceedings of interspeech, pp. 1529\u20131532.","DOI":"10.21437\/Interspeech.2011-322"},{"key":"9324_CR25","doi-asserted-by":"crossref","unstructured":"Rodriguez-Fuentes, L. J., Br\u00fcmmer, N., Penagarikano, M., Varona, A., Diez, M., & Bordel, G. (2012a). The Albayzin 2012 language recognition evaluation plan (Albayzin 2012 LRE). URL: http:\/\/iberspeech2012.ii.uam.es\/images\/PDFs\/albayzin_lre12_evalplan_v1.3_springer","DOI":"10.21437\/Interspeech.2013-387"},{"key":"9324_CR26","unstructured":"Rodriguez-Fuentes, L. J., Penagarikano, M., Varona, A., Diez, M., & Bordel, G. (2012b). KALAKA-2: a TV broadcast speech database for the recognition of Iberian languages in clean and noisy environments. In Proceedings of the LREC (pp. 99\u2013105). Turkey: Istanbul."},{"key":"9324_CR27","unstructured":"Rodriguez-Fuentes, L. J., Varona, A., Diez, M., Penagarikano, M., & Bordel, G. (2012c). Evaluation of spoken language recognition technology using broadcast speech: Performance and challenges. In: Odyssey 2012: The speaker and language recognition workshop, Singapore."},{"key":"9324_CR28","doi-asserted-by":"crossref","unstructured":"Rodriguez-Fuentes, L. J., Penagarikano, M., Varona, A., Diez, M., & Bordel, G. (2013). The Albayzin 2012 language recognition evaluation. In Proceedings of interspeech, pp 1497\u20131501.","DOI":"10.21437\/Interspeech.2013-387"},{"key":"9324_CR29","unstructured":"Schwarz, P. (2008) Phoneme recognition based on long temporal context. PhD thesis, Faculty of Information Technology, Brno University of Technology. http:\/\/www.fit.vutbr.cz\/ . Brno, Czech Republic."},{"key":"9324_CR30","doi-asserted-by":"crossref","unstructured":"Stolcke, A. (2002). SRILM-an extensible language modeling toolkit. In Proceedings of interspeech, pp. 257\u2013286.","DOI":"10.21437\/ICSLP.2002-303"},{"key":"9324_CR31","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P. A., Singer, E., Kohler, M. A., Greene, R. J., Reynolds, D. A., & Deller, J. R. (2002). Approaches to language identification using Gaussian mixture models and shifted Delta Cepstral features. In Proceedings of ICSLP (Interspeech), pp. 89\u201392.","DOI":"10.21437\/ICSLP.2002-74"},{"issue":"8","key":"9324_CR32","first-page":"1181","volume":"88","author":"A Waibel","year":"2000","unstructured":"Waibel, A., Geutner, P., Tomoyiko, L. M., Schultz, T., & Woszczyna, M. (2000). Multilinguality in speech and spoken language systems. Proceedings of the IEEE, Special Issue on Spoken Language Processing, 88(8), 1181\u20131190.","journal-title":"Proceedings of the IEEE, Special Issue on Spoken Language Processing"},{"key":"9324_CR33","volume-title":"The HTK book (for HTK Version 3.4)","author":"S Young","year":"2006","unstructured":"Young, S., Evermann, G., Gales, M., Hain, T., Kershaw, D., Lui, X., et al. (2006). The HTK book (for HTK Version 3.4). Cambridge, UK: Entropic, Ltd."},{"issue":"8","key":"9324_CR34","first-page":"1166","volume":"88","author":"VW Zue","year":"2000","unstructured":"Zue, V. W., & Glass, J. R. (2000). Conversational interfaces: Advances and challenges. Proceedings of the IEEE, Special Issue on Spoken Language Processing, 88(8), 1166\u20131180.","journal-title":"Proceedings of the IEEE, Special Issue on Spoken Language Processing"}],"container-title":["Language Resources and Evaluation"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-015-9324-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10579-015-9324-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10579-015-9324-5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,16]],"date-time":"2023-08-16T06:36:11Z","timestamp":1692167771000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10579-015-9324-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2015,12,19]]},"references-count":34,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2016,6]]}},"alternative-id":["9324"],"URL":"https:\/\/doi.org\/10.1007\/s10579-015-9324-5","relation":{},"ISSN":["1574-020X","1574-0218"],"issn-type":[{"type":"print","value":"1574-020X"},{"type":"electronic","value":"1574-0218"}],"subject":[],"published":{"date-parts":[[2015,12,19]]}}}